MLLM生成网页的跨环境兼容性研究
原标题：Does It Render Everywhere? A Study of Cross-Environment Compatibility in MLLM-Generated Webpages
AI 摘要
本研究首次系统性地评估了多模态大语言模型（MLLM）生成网页的跨环境兼容性。研究者构建了包含2032个标注实例的WebCompat数据集，涵盖8种AI工具生成的网页在9种浏览器和设备组合下的渲染情况。研究发现68%的生成网页存在至少一个兼容性问题，主要症状为页面级布局失败（88.3%），根因包括缺失viewport meta标签（46%）和缺乏弹性布局（29.5%）。基于此，研究者开发了轻量级检测器XCompat，其F1分数达到0.903，优于现有工具。
正文节选
Does It Render Everywhere? A Study of Cross-Environment Compatibility in MLLM-Generated Webpages Abstract Multimodal Large Language Models (MLLMs) have been increasingly adopted to automate webpage generation from visual designs (e.g., screenshots). However, existing evaluations are limited to visual fidelity assessment under a fixed browser-device configuration. Such a setting overlooks the cross-environment rendering compatibility for real-world deployments. To address this gap, we present the